Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: google/gemma-4-E2B-it text-only mode seems uses more VRAM than multimodal-mode

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Code Example

docker pull vllm/vllm-openai:v0.20.1

---

name: vllm-deploy
services:
  vllm:
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    volumes:
      - ${PWD}/.cache/:/root/.cache/
    ports:
      - 8791:8000
    env_file:
      - path: ${PWD}/vllm/.env
    image: vllm/vllm-openai:v0.20.1
    command: >
      google/gemma-4-E2B-it
      --max-model-len 1024
      --max_num_batched_tokens 1024
      --max-num-seqs 1
      --gpu-memory-utilization 0.95
      --no-enable-prefix-caching
      --trust-remote-code
      --limit-mm-per-prompt '{"image":1, "video": 1, "audio": 1}'

---

name: vllm-deploy
services:
  vllm:
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    volumes:
      - ${PWD}/.cache/:/root/.cache/
    ports:
      - 8791:8000
    env_file:
      - path: ${PWD}/vllm/.env
    image: vllm/vllm-openai:v0.20.1
    command: >
      google/gemma-4-E2B-it
      --max-model-len 1024
      --max_num_batched_tokens 1024
      --max-num-seqs 1
      --gpu-memory-utilization 0.95
      --no-enable-prefix-caching
      --trust-remote-code
      --limit-mm-per-prompt '{"image":0, "video": 0, "audio": 0}'
RAW_BUFFERClick to expand / collapse

Your current environment

docker pull vllm/vllm-openai:v0.20.1

I use docker image.

🐛 Describe the bug

When I enable modalities (image=1, video=1, audio=1), vllm seems able to load on RTX 3060 VRAM 12 GB,

name: vllm-deploy
services:
  vllm:
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    volumes:
      - ${PWD}/.cache/:/root/.cache/
    ports:
      - 8791:8000
    env_file:
      - path: ${PWD}/vllm/.env
    image: vllm/vllm-openai:v0.20.1
    command: >
      google/gemma-4-E2B-it
      --max-model-len 1024
      --max_num_batched_tokens 1024
      --max-num-seqs 1
      --gpu-memory-utilization 0.95
      --no-enable-prefix-caching
      --trust-remote-code
      --limit-mm-per-prompt '{"image":1, "video": 1, "audio": 1}'

but when I configure to use text-only,

name: vllm-deploy
services:
  vllm:
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    volumes:
      - ${PWD}/.cache/:/root/.cache/
    ports:
      - 8791:8000
    env_file:
      - path: ${PWD}/vllm/.env
    image: vllm/vllm-openai:v0.20.1
    command: >
      google/gemma-4-E2B-it
      --max-model-len 1024
      --max_num_batched_tokens 1024
      --max-num-seqs 1
      --gpu-memory-utilization 0.95
      --no-enable-prefix-caching
      --trust-remote-code
      --limit-mm-per-prompt '{"image":0, "video": 0, "audio": 0}'

isn't text-only mode be using less VRAM?

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#device allocation#model download#tokenizer error#prompt formatting#chain error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING